Corrigendum: TorbeamNN: machine learning-based steering of ECH mirrors on KSTAR (Plasma Phys. Control. Fusion (2025) 67 (055036) DOI: 10.1088/1361-6587/add08b)

Andrew Rothstein, Minseok Kim, Minho Woo, Minsoo Cha, Cheolsik Byun, Sangkyeun Kim, Keith Erickson, Youngho Lee, Joshua Josephy-Zack, Jalal Butt, Ricardo Shousha, Mi Joung, June Woo Juhn, Kyu Dong Lee, Egemen Kolemen

Research output: Contribution to journalComment/debatepeer-review

Abstract

There was a miscalculation while verifying the performance of the real-time electron density reconstruction model. The previous version stated: ‘For the accuracy of the ne reconstruction, we look to [1] where the mean squared error was found to be 1.31×1017 m−3 using data from the 2023 KSTAR campaign.’ This value should be corrected to be ‘For the accuracy of the ne reconstruction, we look to [1] where the root mean squared error was found to be 1.15×1018 m−3 and the median and mean absolute percentage errors are 1.85% and 2.38%, respectively using data from the 2023 KSTAR campaign.’ The interpretation of this error does not change as the percent error of the ne reconstruction model is substantially lower than the other errors present in the real-time system and consequently does not have an impact on the accuracy of our model.

Original languageEnglish (US)
Article number079501
JournalPlasma Physics and Controlled Fusion
Volume67
Issue number7
DOIs
StatePublished - Jul 31 2025

All Science Journal Classification (ASJC) codes

  • Nuclear Energy and Engineering
  • Condensed Matter Physics

Fingerprint

Dive into the research topics of 'Corrigendum: TorbeamNN: machine learning-based steering of ECH mirrors on KSTAR (Plasma Phys. Control. Fusion (2025) 67 (055036) DOI: 10.1088/1361-6587/add08b)'. Together they form a unique fingerprint.

Cite this